Qiaomu Codex Imagegen
joeseesun/qiaomu-codex-imagegen
Generate or edit images with Codex's built-in image generation from any agent, through an MCP tool or a plain CLI.
A skill your agent uses for image-heavy Codex work when generated or inspected media should stay behind a bounded MCP boundary and the controlling task should receive only durable Job IDs, hashes…
Install Image Context Runtime
$ npx skills add shixinnt/codex-image-context-runtime --skill image-context-runtime -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install shixinnt/codex-image-context-runtime image-context-runtime --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/shixinnt/codex-image-context-runtime.git skills-src && mkdir -p .claude/skills && cp -r skills-src/plugins/codex-image-context-runtime/skills/image-context-runtime .claude/skills/image-context-runtime && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "image-context-runtime" agent skill from https://github.com/shixinnt/codex-image-context-runtime/tree/main/plugins/codex-image-context-runtime/skills/image-context-runtime into .claude/skills/image-context-runtime/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "image-context-runtime", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/shixinnt/codex-image-context-runtime/tree/main/plugins/codex-image-context-runtime/skills/image-context-runtimeType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add shixinnt/codex-image-context-runtime --skill image-context-runtime -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install shixinnt/codex-image-context-runtime image-context-runtime --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/shixinnt/codex-image-context-runtime.git skills-src && mkdir -p .agents/skills && cp -r skills-src/plugins/codex-image-context-runtime/skills/image-context-runtime .agents/skills/image-context-runtime && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "image-context-runtime" agent skill from https://github.com/shixinnt/codex-image-context-runtime/tree/main/plugins/codex-image-context-runtime/skills/image-context-runtime into .agents/skills/image-context-runtime/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "image-context-runtime", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add shixinnt/codex-image-context-runtime --skill image-context-runtime -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install shixinnt/codex-image-context-runtime image-context-runtime --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/shixinnt/codex-image-context-runtime.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/plugins/codex-image-context-runtime/skills/image-context-runtime .cursor/skills/image-context-runtime && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "image-context-runtime" agent skill from https://github.com/shixinnt/codex-image-context-runtime/tree/main/plugins/codex-image-context-runtime/skills/image-context-runtime into .cursor/skills/image-context-runtime/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "image-context-runtime", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/shixinnt/codex-image-context-runtime.git --path plugins/codex-image-context-runtime/skills/image-context-runtime--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add shixinnt/codex-image-context-runtime --skill image-context-runtime -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install shixinnt/codex-image-context-runtime image-context-runtime --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/shixinnt/codex-image-context-runtime.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/plugins/codex-image-context-runtime/skills/image-context-runtime .gemini/skills/image-context-runtime && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "image-context-runtime" agent skill from https://github.com/shixinnt/codex-image-context-runtime/tree/main/plugins/codex-image-context-runtime/skills/image-context-runtime into .gemini/skills/image-context-runtime/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "image-context-runtime", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install shixinnt/codex-image-context-runtime image-context-runtimeInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add shixinnt/codex-image-context-runtime --skill image-context-runtime -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/shixinnt/codex-image-context-runtime.git skills-src && mkdir -p .github/skills && cp -r skills-src/plugins/codex-image-context-runtime/skills/image-context-runtime .github/skills/image-context-runtime && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "image-context-runtime" agent skill from https://github.com/shixinnt/codex-image-context-runtime/tree/main/plugins/codex-image-context-runtime/skills/image-context-runtime into .github/skills/image-context-runtime/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "image-context-runtime", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add shixinnt/codex-image-context-runtime --skill image-context-runtime -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install shixinnt/codex-image-context-runtime image-context-runtime --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/shixinnt/codex-image-context-runtime.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/plugins/codex-image-context-runtime/skills/image-context-runtime .opencode/skills/image-context-runtime && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "image-context-runtime" agent skill from https://github.com/shixinnt/codex-image-context-runtime/tree/main/plugins/codex-image-context-runtime/skills/image-context-runtime into .opencode/skills/image-context-runtime/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "image-context-runtime", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
image-context-runtime- GitHub stars
- 100
- Token cost
- ~723 tokens
- SKILL.md length
- 377 words
- Files
- 1
- Skills in repo
- 1
- Repo updated
- First seen
- Licence
- Apache-2.0
At a glance
A skill your agent uses for image-heavy Codex work when generated or inspected media should stay behind a bounded MCP boundary and the controlling task should receive only durable Job IDs, hashes…
- Works in 7 steps: Confirm one bounded prompt, output name,… → Call submit_image_generation. → Keep the returned job_id. → …
- Image-heavy Codex work when generated
- SKILL.md covers Core boundary, Generate an image, Inspect an image and Restart and recovery, plus 1 more section
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Image Context Runtime is an agent skill from shixinnt/codex-image-context-runtime. Use for image-heavy Codex work when generated or inspected media should stay behind a bounded MCP boundary and the controlling task should receive only durable Job IDs, hashes, relative references, and compact text handoffs.
Its SKILL.md is about 720 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
It sits in Media & Creative, covering Image generation and MCP servers. It works with Model Context Protocol and Node.js. The repository describes itself as: A Codex plugin and local MCP runtime for context-bounded image generation and inspection. The licence is Apache-2.0.
When your agent uses it
- Image-heavy Codex work when generated
- Inspected media should stay behind a bounded MCP boundary and the controlling task should receive only durable Job IDs
- Relative references
- Compact text handoffs
Example prompts
- “/image-context-runtime”
Workflow steps
7 steps, taken from the first numbered list in SKILL.md.
- Confirm one bounded prompt, output name, size, quality, and stable idempotency key.
- Call submit_image_generation.
- Keep the returned job_id.
- Poll with get_image_job; do not resubmit the same intent.
- When terminal, call get_image_handoff.
- Report the relative artifact ref, SHA-256, dimensions, and compact handoff.
- Do not load the generated image into the controlling task unless the user needs direct visual judgment.
What it can do on your machine
Read from SKILL.md and the folder at commit b067f0e. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
No scripts in the folder and no shell commands in SKILL.md.
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Image Context Runtime loads about 723 tokens when it runs. Until then it costs about 62 tokens; SKILL.md has 377 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
The full file from shixinnt/codex-image-context-runtime at commit b067f0e, republished under its Apache-2.0 licence (© shixinnt). 377 words, ~723 tokens.
Download SKILL.mdSave it as
.claude/skills/image-context-runtime/SKILL.md (or your agent's skills folder).- name
- image-context-runtime
- description
- Use for image-heavy Codex work when generated or inspected media should stay behind a bounded MCP boundary and the controlling task should receive only durable Job IDs, hashes, relative references, and compact text handoffs.
Image Context Runtime
Use this workflow for repeated image generation, image inspection, storyboard work, design assets, visual research, or visual QA when returning raw media through the controlling task would add unnecessary context pressure.
Core boundary
- Treat the local Runtime as the owner of image bytes and durable Job state.
- Do not ask an MCP tool to return an image, data URL, base64 payload, or raw Provider response.
- Keep the controlling task text-only unless the user explicitly asks Codex to open a particular image.
- An explicit image open is a separate visual-context decision; this plugin does not make it free.
- The default mock Provider is offline. A real Provider must be explicitly configured and may incur cost.
Generate an image
- Confirm one bounded prompt, output name, size, quality, and stable idempotency key.
- Call
<code>submit_image_generation</code>. - Keep the returned
<code>job_id</code>. - Poll with
<code>get_image_job</code>; do not resubmit the same intent. - When terminal, call
<code>get_image_handoff</code>. - Report the relative artifact ref, SHA-256, dimensions, and compact handoff.
- Do not load the generated image into the controlling task unless the user needs direct visual judgment.
Inspect an image
- Use a path under a configured workspace root. Never send inline media.
- Ask one bounded inspection question.
- Call
<code>submit_image_inspection</code>with a stable idempotency key. - Poll by Job ID.
- Retrieve the bounded inspection handoff.
- Make clear that the handoff is Provider analysis, not human approval.
Show full SKILL.md (139 more words)Show less
Restart and recovery
- Completed jobs remain queryable by Job ID after restart.
- A queued pre-dispatch job may resume safely.
- A job interrupted after Provider dispatch can enter
<code>needs_review</code>. - Do not automatically redispatch an ambiguous paid request.
- Use
<code>resume_image_job</code>only after reviewing its diagnostic and acknowledging possible duplicate cost when the tool requires it.
Failure behavior
- If workspace roots are not configured, stop and provide the configuration command.
- If a path is absolute, outside the configured roots, traverses upward, or escapes through a symlink, do not work around the rejection.
- If the public-result budget is exceeded, return the bounded diagnostic rather than provider data.
- If another live process owns the Runtime directory, do not delete its lock; stop that worker or use a distinct configuration and Runtime directory.
- Never echo API keys, authorization headers, private configuration, or raw exception bodies.
© shixinnt, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
Just SKILL.md in plugins/codex-image-context-runtime/skills/image-context-runtime of shixinnt/codex-image-context-runtime.
Open the folder on GitHubat commit b067f0e
Compare with similar skills
Image Context Runtime next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Image Context Runtime this skillshixinnt/codex-image-context-runtime | 100 | — | ~723 | Automated safety check: Pass | Apache-2.0 | |
| Qiaomu Codex Imagegenjoeseesun/qiaomu-codex-imagegen | 114 | — | ~2.3k | Automated safety check: Pass | MIT | |
| Beatdesign WorkspaceBeatAPI/BeatDesign | 114 | — | ~1.1k | Automated safety check: Pass | Apache-2.0 | |
| Beatdesign WorkspaceBeatAPI/BeatDesign | 114 | — | ~1.3k | Automated safety check: Pass | Apache-2.0 | |
| Cullglebis/claude-skills | 389 | — | ~1.9k | Automated safety check: Pass | MIT | |
| Pascal 3D Scene Editingpascalorg/editor | 25k | — | ~2.9k | Automated safety check: Pass | MIT |
Similar skills
Beatdesign Workspace
BeatAPI/BeatDesign
Operate a local BeatDesign project through MCP when the user asks to create, organize, generate, inspect, or edit media in BeatDesign, including captions, tail-frame continuation, and opening the…
Beatdesign Workspace
BeatAPI/BeatDesign
Operate a local BeatDesign project through MCP when the user asks to create, organize, generate, inspect, or edit media in BeatDesign, including opening the exact Canvas or Editor in Codex for…
Cull
glebis/claude-skills
This skill should be used when the user wants to view, review, rate, organize, search, or export images / AI-art generations with the Cull app.
Pascal 3D Scene Editing
pascalorg/editor
Connects an agent to Pascal's MCP tools to create, inspect, edit, validate and save editable 3D building scenes, then return a verified editor link.
Gemini Skill
WJZ-P/gemini-skill
通过 Gemini 官网（gemini.google.com）执行生图、对话等操作。用户提到"生图/画图/绘图/nano banana/nanobanana/生成图片"等关键词时触发。操作方式分三级优先级：首选 MCP 工具 → 次选 Skill 脚本 → 最次连接 Skill 浏览器手动操作（需用户授权）。禁止自行启动外部浏览器访问 Gemini。
Related
Works with
Categories
Questions about Image Context Runtime
What does Image Context Runtime do?
A skill your agent uses for image-heavy Codex work when generated or inspected media should stay behind a bounded MCP boundary and the controlling task should receive only durable Job IDs, hashes…. Image Context Runtime is an agent skill from shixinnt/codex-image-context-runtime. Use for image-heavy Codex work when generated or inspected media should stay behind a bounded MCP boundary and the controlling task should receive only durable Job IDs, hashes, relative references, and compact text handoffs.
When should I use Image Context Runtime?
Image Context Runtime fits situations like: image-heavy Codex work when generated; inspected media should stay behind a bounded MCP boundary and the controlling task should receive only durable Job IDs; relative references; compact text handoffs.
How do I install Image Context Runtime in Claude Code?
Run `npx skills add shixinnt/codex-image-context-runtime --skill image-context-runtime -a claude-code`. Or copy the skill folder (plugins/codex-image-context-runtime/skills/image-context-runtime in shixinnt/codex-image-context-runtime) into .claude/skills/image-context-runtime in your project. Claude Code loads it when a task matches its description.
How do I install Image Context Runtime in Codex?
Run `npx skills add shixinnt/codex-image-context-runtime --skill image-context-runtime -a codex`. Or copy the skill folder (plugins/codex-image-context-runtime/skills/image-context-runtime in shixinnt/codex-image-context-runtime) into .agents/skills/image-context-runtime in your project. Codex loads it when a task matches its description.
Can I use Image Context Runtime in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add shixinnt/codex-image-context-runtime --skill image-context-runtime -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/image-context-runtime, .gemini/skills/image-context-runtime, .github/skills/image-context-runtime and .opencode/skills/image-context-runtime in your project.
What does Image Context Runtime need to run?
SKILL.md names no scripts, command-line tools or credentials: Image Context Runtime is instructions for the agent only.
Does Image Context Runtime access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is Image Context Runtime safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does Image Context Runtime use?
Image Context Runtime is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Image Context Runtime use?
About 723 tokens (SKILL.md is roughly 2.9k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Image Context Runtime?
Skills that share tags, products or a category with Image Context Runtime: Qiaomu Codex Imagegen (joeseesun/qiaomu-codex-imagegen, 114 stars), Beatdesign Workspace (BeatAPI/BeatDesign, 114 stars), Beatdesign Workspace (BeatAPI/BeatDesign, 114 stars) and Cull (glebis/claude-skills, 389 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Image Context Runtime?
shixinnt (a GitHub user) maintains it in shixinnt/codex-image-context-runtime, which has 100 GitHub stars. The repository was last updated on August 15, 2026.
Source: shixinnt/codex-image-context-runtime on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.